replace __wake function with macro that performs direct syscall

this should generate faster and smaller code, especially with inline
syscalls. the conditional with cnt is ugly, but thankfully cnt is
always a constant anyway so it gets evaluated at compile time. it may
be preferable to make separate __wake and __wakeall macros without a
count argument.

priv flag is not used yet; private futex support still needs to be
done at some point in the future.

src/internal/pthread_impl.h

@@ -106,7 +106,8 @@ void __unmapself(void *, size_t);
 
 int __timedwait(volatile int *, int, clockid_t, const struct timespec *, void (*)(void *), void *, int);
 void __wait(volatile int *, volatile int *, int, int);
-void __wake(volatile int *, int, int);
+#define __wake(addr, cnt, priv) \
+	__syscall(SYS_futex, addr, FUTEX_WAKE, (cnt)<0?INT_MAX:(cnt))
 
 void __acquire_ptc();
 void __release_ptc();

src/thread/__wake.c

-#include "pthread_impl.h"
-#include <limits.h>
-
-void __wake(volatile int *addr, int cnt, int priv)
-{
-	if (priv) priv = 128; priv=0;
-	if (cnt<0) cnt = INT_MAX;
-	__syscall(SYS_futex, (long)addr, FUTEX_WAKE | priv, cnt);
-}